While electroencephalography (EEG)-based brain-computer interfaces (BCIs) have many potential clinical applications, their use is impeded by poor performance for many users. To improve BCI performance, either via enhanced signal processing or user training, it is critical to understand and describe each user's ability to perform mental control tasks and produce discernible EEG patterns. While classification accuracy has predominantly been used to assess user performance, limitations and criticisms of this approach have emerged, thus prompting the need to develop novel user assessment approaches with greater descriptive capability. Here, we propose a combination of unsupervised clustering and Markov chain models to assess and describe user skill.Using unsupervised-means clustering, we segmented the EEG signal space into regions representing pattern states that users could produce. A user's movement through these pattern states while performing different tasks was modeled using Markov chains. Finally, using the steady-state distributions and entropy rates of the Markov chains, we proposed two metricsandto assess, respectively, a user's ability to (i) produce distinct task-specific patterns for each mental task and (ii) maintain consistent patterns during individual tasks.Analysis of data from 14 adolescents using a three-class BCI revealed significant correlations between theandmetrics and classification F1 score. Moreover, analysis of the pattern states and Markov chain models yielded descriptive information regarding user performance not immediately apparent from classification accuracy.Our proposed user assessment method can be used in concert with classifier-based analysis to further understand the extent to which users produce task-specific, time-evolving EEG patterns. In turn, this information could be used to enhance user training or classifier design.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1088/1741-2552/ad17f2 | DOI Listing |
Am J Orthod Dentofacial Orthop
February 2025
Department of Orthodontics, Faculty of Dentistry, Çanakkale Onsekiz Mart University, Çanakkale, Turkey.
Introduction: This study aimed to assess the precision of an open-source, clinician-trained, and user-friendly convolutional neural network-based model for automatically segmenting the mandible.
Methods: A total of 55 cone-beam computed tomography scans that met the inclusion criteria were collected and divided into test and training groups. The MONAI (Medical Open Network for Artificial Intelligence) Label active learning tool extension was used to train the automatic model.
Clin Nutr ESPEN
January 2025
Department of Gastroenterology and Hepatology, Intestinal Failure Unit, Radboud University Medical Centre Nijmegen, Geert Grooteplein 10, 6500 HB, Nijmegen, The Netherlands. Electronic address:
Background And Aims: Measurement of the urine sodium concentration (USC) is a simple procedure that in many patients adequately indicates their hydration status. This is of particular importance in patients suffering from short bowel syndrome (SBS), who may very rapidly dehydrate and are at risk for permanently compromising their kidney function. A point of care test (POCT) that allows reliable measurement of USC would enable these patients to effectively evaluate their sodium- and water balance in the at home setting, thereby avoiding hospital visits and delayed test results.
View Article and Find Full Text PDFJ Biomech
January 2025
Department of Orthopedic Surgery and Orthopedic Research Institute, West China Hospital, Sichuan University Chengdu Sichuan Province China. Electronic address:
OpenCap, a smartphone-based markerless system, offers a cost-effective alternative to traditional marker-based systems for gait analysis. However, its kinematic measurement accuracy must be evaluated before widespread use in clinical practice. This study aimed to evaluate OpenCap for lower-limb joint angle measurements during walking in patients with knee osteoarthritis (OA) and to compare error metrics between patients and healthy controls.
View Article and Find Full Text PDFMidwifery
January 2025
University of Southern Denmark, Unit for Health Promotion Research, Degnevej 14, 6705 Esbjerg, Denmark.
Problem: Despite solid evidence and national recommendations supporting midwife-led continuity-of-care models, Danish women's access to such programs remains limited.
Background: A public birth facility introduced a midwife-led continuity-of-care model, targeting a subset of women receiving antenatal and intrapartum care.
Aim: To compare care satisfaction during pregnancy and birth and birth experience between women receiving midwife-led continuity of care and those receiving standard midwifery care.
Discov Oncol
January 2025
School of Medicine, Hamadan University of Medical Sciences, Pajoohesh Blvd, Hamadan, Iran.
Purpose: Paraneoplastic syndromes (PNS) are a group of rare disorders triggered by an immune response to malignancy, characterized by diverse neurological, muscular, and systemic symptoms. This study aims to leverage machine learning to develop a predictive model for cancer diagnosis in patients with paraneoplastic autoantibodies.
Methods: Demographic data included age and sex, and presenting symptoms were recorded.
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!